Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    AC Voltage

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lakini
    0.50
     echte
    0.46
     遅
    0.46
     കിട
    0.45
    午
    0.45
     diğer
    0.44
    得出
    0.44
    に出
    0.44
     Coordinating
    0.43
     cộng
    0.43
    POSITIVE LOGITS
     बघेल
    0.46
    usso
    0.45
     Gallardo
    0.45
    Azure
    0.45
     வாக்கு
    0.45
    ina
    0.44
     privés
    0.44
    த்தது
    0.44
    ಸ್ಕೊ
    0.43
    it
    0.43
    Act Density 0.000%

    No Known Activations